spark读取ES数据

最新推荐文章于 2025-05-07 22:24:24 发布

TracyGao01

最新推荐文章于 2025-05-07 22:24:24 发布

阅读量8.3k

点赞数

CC 4.0 BY-SA版权

分类专栏： spark 文章标签： spark

本文链接：https://blog.csdn.net/u012551524/article/details/79319718

spark 专栏收录该内容

21 篇文章

订阅专栏

maven pom依赖配置：

<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch-spark-13_2.10</artifactId>
<version>6.1.2</version>
</dependency>

code:

import org.apache.spark.{SparkConf, SparkContext}
import org.elasticsearch.spark._

object ReadEs {
def main(args: Array[String]){

System.setProperty("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
System.setProperty("hadoop.home.dir", "C:\\hadoop-2.6.0-cdh5.11.0")
val conf = new SparkConf().setAppName("READES").setMaster("local").set("es.nodes","172.18.10.34")

val sc = new SparkContext(conf)

// val query = """{"query" : { "match" : { "content" : "上海" }}}"""
// val query = """{"query" : { "match" : { "_id" : 1 }}}"""
// val RDD = sc.esRDD("tracy/fulltext",query)

val RDD = sc.esRDD("tracy/fulltext")

RDD.collect().foreach(x=> (println(x._1,x._2)))

sc.stop()

}

}